© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44246
    Prev
    Next
    INDEX
    Explanations

    Insert, alternative, tuned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åIJİè¿ĽçĶŁ
    -0.07
    illar
    -0.06
    omat
    -0.06
    iante
    -0.06
    erio
    -0.06
    laut
    -0.06
    åľ¨ä¸ĭè½½
    -0.06
    mica
    -0.06
    orza
    -0.06
    .persist
    -0.06
    POSITIVE LOGITS
    zan
    0.08
    以ä¸Ĭ
    0.08
     dentre
    0.07
    æİĴè¡Įæ¦ľåįķ
    0.07
    åħ¶å®ĥ
    0.07
    ãģ¾ãģĹãģ¦
    0.07
    æľĢéĩįè¦ģçļĦæĺ¯
    0.07
    æł¹æľ¬å°±æĺ¯
    0.07
    esh
    0.07
    å¹²èĦĨ
    0.07
    Activations Density 0.017%

    No Known Activations